Whole brain Probabilistic Generative Model toward Realizing Cognitive Architecture for Developmental Robots

@article{Taniguchi2022WholeBP,
  title={Whole brain Probabilistic Generative Model toward Realizing Cognitive Architecture for Developmental Robots},
  author={Tadahiro Taniguchi and Hiroshi Yamakawa and Takayuki Nagai and Kenji Doya and Masamichi Sakagami and Masahiro Suzuki and Tomoaki Nakamura and Akira Taniguchi},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2022},
  volume={150},
  pages={
          293-312
        }
}

Brain-inspired probabilistic generative model for double articulation analysis of spoken language

TLDR
This study compared, mapped, and integrated existing computational models with neuroscientific findings to bridge the gap and provides novel insights that will be foundational to further exploring DAA in the brain.

A survey of multimodal deep generative models

TLDR
A categorized survey of studies on multimodal deep generative models based on variational autoencoders, which are suitable for accomplishing the inference of shared representations from arbitrary modalities and cross-modal generation via these representations.

Hippocampal formation-inspired probabilistic generative model

What is the role of the next generation of cognitive robotics?

TLDR
This paper summarized the discussion focusing on the creation of several cognitive functions without stopping even if the robots face novel uncertainty in daily life, and the importance of setting primitive but concrete targets for cognitive robotics research as cognitive robotics problems.

Semiotically adaptive cognition: toward the realization of remotely-operated service robots for the new normal symbiotic society

TLDR
This paper argues that the development of semiotically adaptive cognitive systems is key to the installation of service robotics technologies in the authors' service environments and describes three challenges: the learning of local knowledge, the acceleration of onsite and online learning, and the augmentation of human–robot interactions.

References

SHOWING 1-10 OF 208 REFERENCES

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

TLDR
This article will discuss how a generalization of the reinforcement learning or optimal control problem, which is sometimes termed maximum entropy reinforcement learning, is equivalent to exact probabilistic inference in the case of deterministic dynamics, and variational inference inThe case of stochastic dynamics.

Hippocampal formation-inspired probabilistic generative model

Neuro-SERKET: Development of Integrative Cognitive System Through the Composition of Deep Probabilistic Generative Models

TLDR
Neuro-SERKET is an extension of SERKET, which can compose elemental PGMs developed in a distributed manner and provide a scheme that allows the composed PGMs to learn throughout the system in an unsupervised way.

Online spatial concept and lexical acquisition with simultaneous localization and mapping

TLDR
An online learning algorithm based on a Rao-Blackwellized particle filter for spatial concept acquisition and mapping and a novel method integrating SpCoA and FastSLAM in the theoretical framework of the Bayesian generative model.

The Hippocampus as a Cognitive Map

Cognitive maps in rats and men.

  • E. Tolman
  • Psychology, Biology
    Psychological review
  • 1948
TLDR
Most of the rat investigations, which I shall report, were carried out in the Berkeley laboratory, and a few, though a very few, were even carried out by me myself.

Semantic mapping for mobile robotics tasks: A survey

OpenRatSLAM: an open source brain-based SLAM system

TLDR
OpenRatSLAM is described, an open-source version of RatSLAM with bindings to the Robot Operating System framework to leverage advantages such as robot and sensor abstraction, networking, data playback, and visualization.

Symbol emergence in robotics: a survey

TLDR
Some state-of-art research topics concerning SER are described, such as multimodal categorization, word discovery, and double articulation analysis, which enable robots to discover words and their embodied meanings from raw sensory-motor information, including visual information, haptic information, auditory information, and acoustic speech signals, in a totally unsupervised manner.
...